中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 多媒体计算与图形学团队
SiamCPN: Visual tracking with the Siamese center-prediction network

文献类型：期刊论文

作者Chen, Dong1,3,4; Tang, Fan2; Dong, Weiming1,3,4; Yao, Hanxing3,5; Xu, Changsheng1,3,4
刊名COMPUTATIONAL VISUAL MEDIA
出版日期2021-06-01
卷号7期号:2页码:253-265
关键词Siamese network single object tracking anchor-free center point detection
ISSN号2096-0433
DOI10.1007/s41095-021-0212-1
通讯作者Dong, Weiming(weiming.dong@ia.ac.cn)
英文摘要Object detection is widely used in object tracking; anchor-free object tracking provides an end-to-end single-object-tracking approach. In this study, we propose a new anchor-free network, the Siamese center-prediction network (SiamCPN). Given the presence of referenced object features in the initial frame, we directly predict the center point and size of the object in subsequent frames in a Siamese-structure network without the need for perframe post-processing operations. Unlike other anchor-free tracking approaches that are based on semantic segmentation and achieve anchor-free tracking by pixel-level prediction, SiamCPN directly obtains all information required for tracking, greatly simplifying the model. A center-prediction sub-network is applied to multiple stages of the backbone to adaptively learn from the experience of different branches of the Siamese net. The model can accurately predict object location, implement appropriate corrections, and regress the size of the target bounding box. Compared to other leading Siamese networks, SiamCPN is simpler, faster, and more efficient as it uses fewer hyperparameters. Experiments demonstrate that our method outperforms other leading Siamese networks on GOT-10K and UAV123 benchmarks, and is comparable to other excellent trackers on LaSOT, VOT2016, and OTB-100 while improving inference speed 1.5 to 2 times.
WOS关键词OBJECT TRACKING
资助项目National Key RAMP;D Program of China[2018YFC0807500] ; National Natural Science Foundation of China[U20B2070] ; National Natural Science Foundation of China[61832016]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000648692900008
出版者SPRINGERNATURE
资助机构National Key RAMP;D Program of China ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/44645]  
专题自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者Dong, Weiming
作者单位1.Chinese Acad Sci, Inst Automat, NLPR, Beijing 100190, Peoples R China
2.Jilin Univ, Sch Artificial Intelligence, Changchun 130012, Peoples R China
3.CASIA LLVISION Joint Lab, Beijing 100190, Peoples R China
4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100040, Peoples R China
5.LLVISION Technol Co LTD, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Chen, Dong,Tang, Fan,Dong, Weiming,et al. SiamCPN: Visual tracking with the Siamese center-prediction network[J]. COMPUTATIONAL VISUAL MEDIA,2021,7(2):253-265.
APA Chen, Dong,Tang, Fan,Dong, Weiming,Yao, Hanxing,&Xu, Changsheng.(2021).SiamCPN: Visual tracking with the Siamese center-prediction network.COMPUTATIONAL VISUAL MEDIA,7(2),253-265.
MLA Chen, Dong,et al."SiamCPN: Visual tracking with the Siamese center-prediction network".COMPUTATIONAL VISUAL MEDIA 7.2(2021):253-265.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。